{"total":147,"rows":[{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279,"area":null},{"id":"2411.04872","title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","created":"2024-11-07","cited_by_count":243,"area":"lr"},{"id":"2502.01534","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","created":"2025-02-03","cited_by_count":125,"area":null},{"id":"2409.19839","title":"ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities","created":"2024-09-30","cited_by_count":110,"area":null},{"id":"2502.06559","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","created":"2025-02-10","cited_by_count":60,"area":null},{"id":"2502.17521","title":"Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation","created":"2025-02-23","cited_by_count":38,"area":null},{"id":"2502.17407","title":"Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning","created":"2025-02-24","cited_by_count":37,"area":"lr"},{"id":"2502.14425","title":"A Survey on Data Contamination for Large Language Models","created":"2025-02-20","cited_by_count":35,"area":null},{"id":"2406.14644","title":"Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediation","created":"2024-06-20","cited_by_count":30,"area":null},{"id":"2503.04550","title":"Benchmarking Reasoning Robustness in Large Language Models","created":"2025-03-06","cited_by_count":30,"area":"lr"},{"id":"2406.17681","title":"VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation","created":"2024-06-25","cited_by_count":29,"area":null},{"id":"2410.18966","title":"Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions","created":"2024-10-24","cited_by_count":26,"area":null},{"id":"2502.15109","title":"Social Genome: Grounded Social Reasoning Abilities of Multimodal Models","created":"2025-02-21","cited_by_count":26,"area":"lr"},{"id":"2508.01059","title":"Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report","created":"2025-08-01","cited_by_count":23,"area":null},{"id":"2411.08324","title":"Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle","created":"2024-11-13","cited_by_count":19,"area":null},{"id":"2603.05344","title":"Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned","created":"2026-03-05","cited_by_count":18,"area":"agents"},{"id":"2410.13961","title":"From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization","created":"2024-10-17","cited_by_count":17,"area":null},{"id":"2502.00678","title":"How Contaminated Is Your Benchmark? Quantifying Dataset Leakage in Large Language Models with Kernel Divergence","created":"2025-02-02","cited_by_count":15,"area":null},{"id":"2503.16402","title":"The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination","created":"2025-03-20","cited_by_count":15,"area":null},{"id":"2410.03249","title":"How Much Can We Forget about Data Contamination?","created":"2024-10-04","cited_by_count":14,"area":null},{"id":"2506.21614","title":"LastingBench: Defend Benchmarks Against Knowledge Leakage","created":"2025-06-21","cited_by_count":14,"area":null},{"id":"2509.13333","title":"Evaluation Awareness Scales Predictably in Open-Weights Large Language Models","created":"2025-09-10","cited_by_count":14,"area":null},{"id":"2503.13572","title":"VeriContaminated: Assessing LLM-Driven Verilog Coding for Data Contamination","created":"2025-03-17","cited_by_count":12,"area":null},{"id":"2607.00053","title":"SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks","created":"2026-06-30","cited_by_count":11,"area":"agents"},{"id":"2410.07114","title":"System 2 thinking in OpenAI's o1-preview model: Near-perfect performance on a mathematics exam","created":"2024-09-19","cited_by_count":10,"area":"lr"},{"id":"2507.11405","title":"DCR: Quantifying Data Contamination in LLMs Evaluation","created":"2025-07-15","cited_by_count":10,"area":null},{"id":"2510.02386","title":"On The Fragility of Benchmark Contamination Detection in Reasoning Models","created":"2025-09-30","cited_by_count":9,"area":"lr"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2410.10880","title":"Fine-tuning can Help Detect Pretraining Data from Large Language Models","created":"2024-10-09","cited_by_count":8,"area":null},{"id":"2412.09460","title":"The Impact of Copyrighted Material on Large Language Models: A Norwegian Perspective","created":"2024-12-12","cited_by_count":8,"area":null},{"id":"2503.12072","title":"Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models","created":"2025-03-15","cited_by_count":8,"area":null},{"id":"2506.00789","title":"RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems","created":"2025-06-01","cited_by_count":8,"area":"rag"},{"id":"2509.24210","title":"BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models","created":"2025-09-29","cited_by_count":8,"area":"lr"},{"id":"2604.06802","title":"Riemann-Bench: A Benchmark for Moonshot Mathematics","created":"2026-04-08","cited_by_count":8,"area":null},{"id":"2604.18543","title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","created":"2026-04-20","cited_by_count":8,"area":null},{"id":"2501.11790","title":"Benchmarking LLMs' Mathematical Reasoning with Unseen Random Variables Questions","created":"2025-01-20","cited_by_count":7,"area":"lr"},{"id":"2504.11239","title":"Nondeterministic Polynomial-time Problem Challenge: An Ever-Scaling Reasoning Benchmark for LLMs","created":"2025-04-15","cited_by_count":7,"area":"lr"},{"id":"2507.17747","title":"Pretraining on the Test Set Is No Longer All You Need: A Debate-Driven Approach to QA Benchmarks","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2507.23009","title":"Position: Stop Evaluating AI with Human Tests, Develop Principled, AI-specific Tests instead","created":"2025-07-30","cited_by_count":7,"area":null},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2406.16382","title":"UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2407.15352","title":"MAVEN-Fact: A Large-scale Event Factuality Detection Dataset","created":"2024-07-22","cited_by_count":6,"area":null},{"id":"2510.09259","title":"Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2607.22368","title":"Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI","created":"2026-07-24","cited_by_count":6,"area":"agents"},{"id":"2505.17241","title":"Generative AI and Creativity: A Systematic Literature Review and Meta-Analysis","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2505.20429","title":"PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2505.24069","title":"Can LLMs Reason Structurally? Benchmarking via the Lens of Data Structures","created":"2025-05-29","cited_by_count":5,"area":"lr"},{"id":"2510.09275","title":"Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation","created":"2025-10-10","cited_by_count":5,"area":"lr"},{"id":"2511.22047","title":"Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks","created":"2025-11-27","cited_by_count":5,"area":"safety"},{"id":"2603.02119","title":"Pencil Puzzle Bench: A Benchmark for Multi-Step Verifiable Reasoning","created":"2026-03-02","cited_by_count":5,"area":"lr"},{"id":"2603.10793","title":"Multilingual Reasoning Gym: Multilingual Scaling of Procedural Reasoning Environments","created":"2026-03-11","cited_by_count":5,"area":null},{"id":"2603.29020","title":"Emergence WebVoyager: Toward Consistent and Transparent Evaluation of (Web) Agents in The Wild","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2603.29403","title":"Security in LLM-as-a-Judge: A Comprehensive SoK","created":"2026-03-31","cited_by_count":5,"area":null},{"id":"2608.23564","title":"SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?","created":"2026-08-24","cited_by_count":5,"area":"agents"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2501.05712","title":"Multi-Step Reasoning in Korean and the Emergent Mirage","created":"2025-01-10","cited_by_count":4,"area":"lr"},{"id":"2503.04840","title":"Framing the Game: How Context Shapes LLM Decision-Making","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2506.07751","title":"AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking","created":"2025-06-09","cited_by_count":4,"area":"lr"},{"id":"2510.04850","title":"Detecting Distillation Data from Reasoning Models","created":"2025-10-06","cited_by_count":4,"area":"lr"},{"id":"2603.09678","title":"EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages","created":"2026-03-10","cited_by_count":4,"area":"lr"},{"id":"2604.07650","title":"A Statistical Framework for Auditing Behavioral Dependence and Induced Bias in LLM Judges","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2605.11504","title":"CTFusion: A CTF-based Benchmark for LLM Agent Evaluation","created":"2026-05-12","cited_by_count":4,"area":"agents"},{"id":"2504.14175","title":"Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion","created":"2025-04-19","cited_by_count":3,"area":"lr"},{"id":"2506.14927","title":"MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance","created":"2025-06-17","cited_by_count":3,"area":"lr"},{"id":"2507.19909","title":"The Impact of Fine-tuning Large Language Models on Automated Program Repair","created":"2025-07-26","cited_by_count":3,"area":null},{"id":"2509.09705","title":"The Non-Determinism of Small LLMs: Evidence of Low Answer Consistency in Repetition Trials of Standard Multiple-Choice Benchmarks","created":"2025-09-05","cited_by_count":3,"area":null},{"id":"2509.14448","title":"VCBench: Benchmarking LLMs in Venture Capital","created":"2025-09-17","cited_by_count":3,"area":null},{"id":"2509.23219","title":"WirelessMathLM: Teaching Mathematical Reasoning for LLMs in Wireless Communications with Reinforcement Learning","created":"2025-09-27","cited_by_count":3,"area":"lr"},{"id":"2511.08042","title":"Towards a Standard, Enterprise-Relevant Agentic AI Benchmark: Lessons from 5.5 billion tokens' worth of agentic AI evaluations","created":"2025-11-11","cited_by_count":3,"area":"agents"},{"id":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2605.21856","title":"The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation","created":"2026-05-21","cited_by_count":3,"area":"lr"},{"id":"2605.26161","title":"TSFMAudit: Data Contamination Auditing in Forecasting Time Series Foundation Models","created":"2026-05-24","cited_by_count":3,"area":null},{"id":"2607.21962","title":"Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings","created":"2026-07-24","cited_by_count":3,"area":"agents"},{"id":"2410.08437","title":"Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks","created":"2024-10-11","cited_by_count":2,"area":"lr"},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2503.21646","title":"Unlocking the Potential of Past Research: Using Generative AI to Reconstruct Healthcare Simulation Models","created":"2025-03-27","cited_by_count":2,"area":null},{"id":"2503.23779","title":"WinoWhat: A Parallel Corpus of Paraphrased WinoGrande Sentences with Common Sense Categorization","created":"2025-03-31","cited_by_count":2,"area":"lr"},{"id":"2504.06324","title":"From Stability to Inconsistency: A Study of Moral Preferences in LLMs","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2504.17198","title":"Automatically Generating Rules of Malicious Software Packages via Large Language Model","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2504.18474","title":"Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions","created":"2025-04-25","cited_by_count":2,"area":null},{"id":"2508.05452","title":"LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2510.08569","title":"ArenaBencher: Automatic Benchmark Evolution via Multi-Model Competitive Evaluation","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2511.09139","title":"MACEval: A Multi-Agent Continual Evaluation Network for Large Models","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2511.10691","title":"Evaluating from Benign to Dynamic Adversarial: A Squid Game for Large Language Models","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2601.22737","title":"Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models","created":"2026-01-30","cited_by_count":2,"area":"mllm"},{"id":"2605.19999","title":"LLM Benchmark Datasets Should Be Contamination-Resistant","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2606.03650","title":"CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2607.10712","title":"Distributed Denial of Science: How Indirect Data Poisoning of AI Systems Can Industrialize Scientific Fraud","created":"2026-07-12","cited_by_count":2,"area":"safety"},{"id":"2607.18269","title":"Wisdom of LLM Crowds: Aggregation and Contamination in Language Model Ensembles","created":"2026-05-26","cited_by_count":2,"area":null},{"id":"2608.02985","title":"Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2608.20290","title":"Phantom Gains: Auditing Self-Improvement Against a Measured Null","created":"2026-08-20","cited_by_count":2,"area":"synth"},{"id":"2609.01552","title":"Can LLMs Discover Scientific Laws in Real and Parallel Worlds?","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2410.11265","title":"In-Context Learning for Long-Context Sentiment Analysis on Infrastructure Project Opinions","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2410.15005","title":"CAP: Data Contamination Detection via Consistency Amplification","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2502.16606","title":"Reasoning about Affordances: Causal and Compositional Reasoning in LLMs","created":"2025-02-23","cited_by_count":1,"area":"lr"},{"id":"2505.15501","title":"Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2505.18978","title":"AI4Math: A Native Spanish Benchmark for University-Level Mathematical Reasoning in Large Language Models","created":"2025-05-25","cited_by_count":1,"area":"lr"},{"id":"2511.21591","title":"On the Limits of Innate Planning in Large Language Models","created":"2025-11-26","cited_by_count":1,"area":null}],"next_cursor":"100"}